Dual-Attention Enhanced BDense-UNet for Liver Lesion Segmentation

TL;DR

This paper introduces DA-BDense-UNet, a novel liver lesion segmentation network combining DenseUNet, bidirectional LSTM, and attention mechanisms to improve feature learning and focus on salient regions.

Contribution

The paper presents a new segmentation model integrating DenseUNet, bidirectional LSTM, and attention gates, enhancing feature representation and segmentation accuracy.

Findings

Achieved comparable dice coefficient performance with state-of-the-art models.

Effectively diminishes background responses and emphasizes salient regions.

Demonstrated robustness across multi-hospital liver CT datasets.

Abstract

In this work, we propose a new segmentation network by integrating DenseUNet and bidirectional LSTM together with attention mechanism, termed as DA-BDense-UNet. DenseUNet allows learning enough diverse features and enhancing the representative power of networks by regulating the information flow. Bidirectional LSTM is responsible to explore the relationships between the encoded features and the up-sampled features in the encoding and decoding paths. Meanwhile, we introduce attention gates (AG) into DenseUNet to diminish responses of unrelated background regions and magnify responses of salient regions progressively. Besides, the attention in bidirectional LSTM takes into account the contribution differences of the encoded features and the up-sampled features in segmentation improvement, which can in turn adjust proper weights for these two kinds of features. We conduct experiments on liver CT image data sets collected from multiple hospitals by comparing them with state-of-the-art segmentation models. Experimental results indicate that our proposed method DA-BDense-UNet has achieved comparative performance in terms of dice coefficient, which demonstrates its effectiveness.